Placebo lead-in design is a design option to lower the impact of high placebo response rates on the success of a clinical trial. In placebo lead-in design all subjects receive placebo first, after which subjects who have not responded to placebo are randomized to placebo versus drug and the efficiency analysis commences. The goal of placebo lead-in trial is to increase the treatment difference in a trial compared to a standard single stage parallel design. Both placebo lead-in and a parallel design can be viewed as special cases of a two-stage design where only placebo non-responders continue in the second stage. Using the framework of the two-stage design we compute the optimal allocation ratio between drug and placebo in stage 1 to determine whether a single stage design, a placebo-lead-in design, or a two-stage design is the best design for a given set of response rates.